# NiLBS: Neural Inverse Linear Blend Skinning Source: [NiLBS: Neural Inverse Linear Blend Skinning]() Collection index: [llms.txt]() Data updated: 2025-10-28T13:56:42.488Z Authors: Timothy Jeruzalski, David I.W. Levin, Alec Jacobson, Paul Lalonde, Mohammad Norouzi, Andrea Tagliasacchi Published: 2020-04-06T20:46:37.000Z ## Abstract In this technical report, we investigate efficient representations of articulated objects (e.g. human bodies), which is an important problem in computer vision and graphics. To deform articulated geometry, existing approaches represent objects as meshes and deform them using "skinning" techniques. The skinning operation allows a wide range of deformations to be achieved with a small number of control parameters. This paper introduces a method to invert the deformations undergone via traditional skinning techniques via a neural network parameterized by pose. The ability to invert these deformations allows values (e.g., distance function, signed distance function, occupancy) to be pre-computed at rest pose, and then efficiently queried when the character is deformed. We leave empirical evaluation of our approach to future work. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [3D Human Reconstruction on Minimally Clothed Humans Within Distribution](): 3D human reconstruction; Minimally Clothed Humans Within Distribution; IoU BBox: 82.08. - [3D Human Reconstruction on Minimally Clothed Humans Out of Distribution](): 3D human reconstruction; Minimally Clothed Humans Out of Distribution; IoU (bbox): 66.93. ## Original sources and implementation [Original paper]() [PDF]()